面向机器人运动规划且具备零样本泛化能力的联邦强化学习
Federated reinforcement learning for robot motion planning with zero-shot generalization
AI总结：
提出一种联邦强化学习框架，使多机器人在不共享原始数据的情况下协作学习运动规划策略，并从到达时间、安全性、收敛性和最优性差距等方面提供零样本泛化理论保证。
摘要：
本文研究学习一种用于机器人运动规划的控制策略问题，该策略需具备零样本泛化能力，即当所学策略部署到新环境时，无需进行数据收集和策略适配。我们开发了一个联邦强化学习框架，使多个学习者与一个中心服务器（即 Cloud）能够在不共享原始数据的情况下进行协作学习。在每次迭代中，每个学习者将其本地控制策略及相应的估计归一化到达时间上传至 Cloud；随后 Cloud 在各学习者之间计算全局最优解，并将最优策略广播给学习者。每个学习者随后在其本地控制策略与来自 Cloud 的策略之间进行选择，以用于下一次迭代。所提出框架利用了所推导的关于到达时间和安全性的零样本泛化保证。本文还给出了关于几乎必然收敛、近似一致、Pareto 改进和最优性差距的理论保证。最后通过 Monte Carlo 仿真对所提出框架进行了评估。
英文摘要：
This paper considers the problem of learning a control policy for robot motion planning with zero-shot generalization, i.e., no data collection and policy adaptation is needed when the learned policy is deployed in new environments. We develop a federated reinforcement learning framework that enables collaborative learning of multiple learners and a central server, i.e., the Cloud, without sharing their raw data. In each iteration, each learner uploads its local control policy and the corresponding estimated normalized arrival time to the Cloud, which then computes the global optimum among the learners and broadcasts the optimal policy to the learners. Each learner then selects between its local control policy and that from the Cloud for next iteration. The proposed framework leverages on the derived zero-shot generalization guarantees on arrival time and safety. Theoretical guarantees on almost-sure convergence, almost consensus, Pareto improvement and optimality gap are also provided. Monte Carlo simulation is conducted to evaluate the proposed framework.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
